© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127699
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on test-related code tokens—e.g. imports from testing libraries and words like “describe,” “it,” and “expect.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    code, testing frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     with
    -1.32
     contains
    -1.20
     includes
    -1.02
     may
    -1.01
     allows
    -0.97
    子が
    -0.95
     including
    -0.94
     руками
    -0.93
    子は
    -0.92
     without
    -0.92
    POSITIVE LOGITS
    তথ্য
    1.09
     okuyayım
    1.05
     日常
    0.99
     miſ
    0.96
     demokrat
    0.96
     schuldig
    0.95
     teolog
    0.93
    然后
    0.93
    Huhu
    0.91
    ansu
    0.90
    Activations Density 0.001%

    No Known Activations